OVERVIEW OF EXISTING METHODS OF AUTONOMOUS VESSELS COLLISION AVOIDANCE

Collision avoidance is vital for safety of navigation at sea. At first scientists aimed at developing navigational assistance systems for supporting human operators in collision prevention and enhancing situational awareness. Nowadays the development of unmanned systems has gained appreciable amount of attention. The main purpose of modern researches is to solve collision avoidance problems. An overview of collision avoidance methods proposed by Russian and foreign researchers is offered iт the paper. The authors offer different techniques for solving the collision avoidance problem, namely, Artificial Potential Fields, Ant Colony Optimisation, Velocity Obstacles and Velocity Resolution Method, Interval Programming, Fuzzy Logic, Neural Networks with different optimisation methods, Optimal Reciprocal Collision Avoidance, combined algorithms. However, some of the articles do not take into account using ship motion models, complying with the International Regulations for Preventing Collisions at Sea and collision avoidance with static objects. Some approaches consider only two-vessels collision avoidance, not all of them are capable of using engine maneuvers. Currents, tides, winds and seas are not considered in any method described in this paper. Many researches have simulation results carried out in computer-based systems, but only a few have results of natural trials. The reviewed researches are divided into three groups: approaches considering avoidance of static and dynamic objects, approaches considering collision avoidance in two-ship encounter situations and approaches considering multi-ship encounter situations. It is noted that the purpose of further researches will be developing the existing approaches, elimination of their deficiencies and supplementing them in order to solve the whole complex of existing problems.

autonomous navigation, unmanned vessel, collision avoidance, collision prevention, neural networks, USV

1. Chauvin C. Human and organisational factors in maritime accidents: Analysis of collisions at sea using the HFACS / C. Chauvin, S. Lardjane, G. Morel, J. P. Clostermann, B. Langard // Accident Analysis & Prevention. - 2013. - Vol. 59. - Pp. 26-37. DOI: 10.1016/j.aap.2013.05.006.

2. Autonomous shipping. IMO [Электронный ресурс] - Режим доступа: https://www.imo.org/en/MediaCentre/HotTopics/Pages/Autonomous-shipping.aspx (дата обращения 29.04.2021).

3. Naeem W. Collision avoidance of maritime vessels / W. Naeem, S. C. de Oliveira Henrique, M. Abu-Tair // Navigation and Control of Autonomous Marine Vehicles. - 2019. - Pp. 61-84. DOI: 10.1049/PBTR011E_ch3.

4. Lazarowska A. Ship’s Trajectory Planning for Collision Avoidance at Sea Based on Ant Colony Optimisation //The Journal of Navigation. - 2015. - Vol. 68. - Pp. 291-307. DOI: 10.1017/S0373463314000708.

5. Bonabeau E. Swarm Intelligence. From Natural to Artificial Systems / E. Bonabeau, M. Dorigo, G. Theraulaz.- Oxford University Press, 1999. - 307 p. DOI: 10.1093/oso/9780195131581.001.0001.

6. Kuwata Y. Safe Maritime Navigation with COLREGS Using Velocity Obstacles / Y. Kuwata, M. T. Wolf, D. Zarzhitsky, T. L. Huntsberger // 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. - IEEE, 2011. - Pp. 4728-4734. DOI: 10.1109/IROS.2011.6094677.

7. Fiorini P. Motion Planning in Dynamic Environments Using Velocity Obstacles / P. Fiorini, Z. Shiller //International Journal of Robotics Research. - 1998. - Vol. 17. - Is. 7. - Pp. 760-772. DOI: 10.1177/027836499801700706.

8. Wang C. Research on intelligent collision avoidance decision-making of unmanned ship in unknown environments / C. Wang, X. Zhang, L. Cong, J. Li, J. Zhang // Evolving Systems. - 2019. - Vol. 10. - Is. 4. - Pp. 649-658. DOI: 10.1007/s12530-018-9253-9.

9. Fan Y. An autonomous dynamic collision avoidance control method for unmanned surface vehicle in unknown ocean environment / Y. Fan, X. Sun, G. Wang // International Journal of Advanced Robotic Systems. - 2019. - Vol. 16. - Is. 2. - Pp. 1729881419831581. DOI: 10.1177/1729881419831581.

10. Седова Н. А. Нейросетевое решение задачи расхождения двух судов в зоне чрезмерного сближения / Н. А. Седова, В. А. Седов // Перспективы развития информационных технологий. Труды Всероссийской молодежной научно-практической конференции. - Кемерово: Кузбасский государственный технический университет имени Т. Ф. Горбачева, 2014. - С. 278-279.

11. Седова Н. А. Метод расхождения морских судов в зоне чрезмерного сближения на основе нейронечетких технологий / Н. А. Седова, В. А. Седов // Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение. - 2018. - Т. 8. - № 4 (29). - С. 53-62.

12. Benjamin M. R. Navigation of Unmanned Marine Vehicles in Accordance with the Rules of the Road / M. R. Benjamin, J. A. Curcio, J. J. Leonard, P. M. Newman // Proceedings of the 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006. - IEEE, 2006. - Pp. 3581-3587. DOI: 10.1109/ROBOT.2006.1642249.

13. Perera L. P. Autonomous Guidance and Navigation based on the COLREGs rules and regulations of collision avoidance / L. P. Perera, J. P. Carvalho, C. G. Soares // Proceedings of the international workshop advanced ship design for pollution prevention. - London, UK: Taylor & Francis Group, 2010. - Pp. 205-216. DOI: 10.1201/b10565-26.

14. Смоленцев С. В. Кооперативное маневрирование безэкипажных судов для безопасного расхождения в море / С. В. Смоленцев, А. Е. Сазонов, Ю. М. Искандеров // Вестник Государственного университета морского и речного флота имени адмирала С. О. Макарова. - 2018. - Т. 10. - № 4. - С. 687-695. DOI: 10.21821/2309-5180-2018-10-4-687-695.

15. Rego F. C. Cooperative path-following control with logic-based communications: Theory and practice / F. C. Rego, N. T. Hung, C. N. Jones, A. M. Pascoal, A. P. Aguiar, S. Sharma, B. Subudhi // Navigation and Control of Autonomous Marine Vehicles. - 2019. - Pp. 187-224. DOI: 10.1049/PBTR011E_ch8.

16. Shen H. Automatic collision avoidance of multiple ships based on deep Q-learning / H. Shen, H. Hashimoto, A. Matsuda, Y. Taniguchi, D. Terada, C. Guo // Applied Ocean Research. - 2019. - Vol. 86. - Pp. 268-288. DOI: 10.1016/j.apor.2019.02.020.

17. Mnih V. Playing Atari with Deep Reinforcement Learning / V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, M. Riedmiller // arXiv preprint arXiv:1312.5602. - 2013. - 9 p.

18. Fossen T. I. Guidance and control of ocean vehicles. Doctors Thesis; University of Trondheim, Norway / T. I. Fossen. - Chichester, England: John Wiley & Sons, 1999. - 494 p.

19. Hu Y. Multi-ship collision avoidance decision-making based on collision risk index / Y. Hu, A. Zhang, W. Tian, J. Zhang, Z. Hou // Journal of Marine Science and Engineering. - 2020. - Vol. 8. - Is. 9. - Pp. 640. DOI: 10.3390/jmse8090640.

20. Zhao Y. A real-time collision avoidance learning system for Unmanned Surface Vessels / Y. Zhao, W. Li, P. Shi // Neurocomputing. - 2016. - Vol. 182. - Pp. 255-266. DOI: 182.10.1016/j.neucom.2015.12.028.

21. Wang Y. M. Environmental impact assessment using the evidential reasoning approach / Y. M. Wang, J. B. Yang, D. L. Xu // European Journal of Operational Research. - 2006. - Vol. 174. - Is. 3. - Pp. 1885-1913. DOI: 10.1016/j.ejor.2004.09.059.

22. Praczyk T. Neural anti-collision system for Autonomous Surface Vehicle / T. Praczyk // Neurocomputing. - 2015. - Vol. 149. - Pp. 559-572. DOI: 10.1016/j.neucom.2014.08.018.

23. Xie S. Ship predictive collision avoidance method based on an improved beetle antennae search algorithm / S. Xie, X. Chu, M. Zheng, C. Liu // Ocean Engineering. - 2019. - Vol. 192. - Pp. 106542. DOI: 10.1016/j.oceaneng.2019.106542.

24. Jiang X. BAS: Beetle antennae search algorithm for optimization problems / X. Jiang, S. Li // International Journal of Robotics and Control. - 2018. - Vol. 1. - No. 1. DOI: 10.5430/ijrc.v1n1p1.

25. Zhang J. A distributed anti-collision decision support formulation in multi-ship encounter situations under COLREGs / J. Zhang, D. Zhang, X. Yan, S. Haugen, C. G. Soares // Ocean Engineering. - 2015. - Vol. 105. - Pp. 336-348. DOI: 10.1016/j.oceaneng.2015.06.054.

26. Zhang J. F. Ship trajectory control optimization on anti-collision maneuvering / J. F. Zhang, D. Yang, D. Zhang, S. Haugen // TransNav: International Journal on Marine Navigation and Safety of Sea Transportation. - 2013. - Vol. 7. - Nr. 1. - Pp. 89-93. DOI: 10.12716/1001.07.01.11.

27. Szlapczynski R. On evolutionary computing in multi-ship trajectory planning / R. Szlapczynski, J. Szlapczynska // Applied Intelligence. - 2012. - Vol. 37. - Is. 2. - Pp. 155-174. DOI: 10.1007/s10489-011-0319-7.

28. Sawada R. Automatic ship collision avoidance using deep reinforcement learning with LSTM in continuous action spaces / R. Sawada, K. Sato, T. Majima // Journal of Marine Science and Technology. - 2020. - Pp. 1-16. DOI: 10.1007/s00773-020-00755-0.

29. Li Y. Deep learning structure for collision avoidance planning of unmanned surface vessel / Y. Li, J. Zheng // Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment. - 2021. - Vol. 235. - Is. 2. - Pp. 511-520. DOI: 10.1177/1475090220970102.

30. Kingma D. P. A method for stochastic optimization / D. P. Kingma, J. Ba // The 3rd-International Conference for Learning Representations, San Diego, 2015. - ICLR, 2015.

31. Guo S. An autonomous path planning model for unmanned ships based on deep reinforcement learning / S. Guo, X. Zhang, Y. Zheng, Y. Du // Sensors. - 2020. - Vol. 20. - Is. 2. - Pp. 426. DOI: 10.3390/s20020426.

32. Xie S. A composite learning method for multi-ship collision avoidance based on reinforcement learning and inverse control / S. Xie, X. Chu, M. Zheng, C. Liu // Neurocomputing. - 2020. - Vol. 411. - Pp. 375-392. DOI: 10.1016/j.neucom.2020.05.089.

33. Abkowitz M. A. Measurement of hydrodynamic characteristics from ship maneuvering trials by system identification / M. A. Abkowitz // Transactions of Society of Naval Architects and Marine Engineers. - 1981. - Vol. 88. - Pp. 283-318.